© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200573
    Prev
    Next
    INDEX
    Explanations

    research investigating writing

    np_acts-logits-general · gemini-2.5-flash-lite

    alphanumeric sequences and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romet
    0.51
    erno
    0.50
    ripe
    0.48
    aliyet
    0.48
    ﻞ
    0.47
    એ
    0.46
    predict
    0.45
    language
    0.45
    르는
    0.44
    endung
    0.44
    POSITIVE LOGITS
     փ
    0.52
     alap
    0.51
     ଆ
    0.50
     ज़ि
    0.48
     traumat
    0.47
     телефо
    0.47
     ți
    0.46
     станда
    0.45
     ח
    0.45
     clocked
    0.45
    Activations Density 0.000%

    No Known Activations